public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Keith Busch <kbusch@fb.com>
To: <linux-nvme@lists.infradead.org>, <linux-block@kernel.vger.org>
Cc: <axboe@kernel.dk>, <hch@lst.de>, Keith Busch <kbusch@kernel.org>
Subject: [RFC 0/4] partial sector read support
Date: Wed, 4 May 2022 09:32:03 -0700	[thread overview]
Message-ID: <20220504163207.891761-1-kbusch@fb.com> (raw)

From: Keith Busch <kbusch@kernel.org>

Don't you just hate that you must read a full sector when you only cared
about a few bytes? Well, good news! Standardized protocols provide a way
for the host to describe unwanted read data, allowing partial sector
access. This lets applications reduce allocated memory that was used to
hold the unwanted data, while also reducing link traffic.

This series enables this for the NVMe protocol through direct io. With
this, a userspace app can read a single contiguous byte range, subject
to hardware DMA constraints. An in-kernel user could theorectically
construct a bio to read multiple discontiguous ranges if desired.

Keith Busch (4):
  block: export dma_alignment attribute
  block: relax direct io memory alignment
  block: add bit bucket support
  nvme: add bit bucket support

 block/blk-core.c          |  5 ++++
 block/blk-merge.c         |  3 +-
 block/blk-mq.c            |  2 ++
 block/blk-sysfs.c         | 10 +++++++
 block/fops.c              | 61 +++++++++++++++++++++++++++++++++------
 drivers/nvme/host/core.c  |  3 ++
 drivers/nvme/host/nvme.h  |  6 ++++
 drivers/nvme/host/pci.c   | 17 +++++++++--
 fs/direct-io.c            | 11 ++++---
 fs/iomap/direct-io.c      |  3 +-
 include/linux/blk-mq.h    |  2 ++
 include/linux/blk_types.h |  1 +
 include/linux/blkdev.h    | 18 ++++++++++++
 include/linux/nvme.h      |  2 ++
 14 files changed, 127 insertions(+), 17 deletions(-)

-- 
2.30.2



             reply	other threads:[~2022-05-04 16:32 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-04 16:32 Keith Busch [this message]
2022-05-04 16:32 ` [RFC 1/4] block: export dma_alignment attribute Keith Busch
2022-05-04 16:32 ` [RFC 2/4] block: relax direct io memory alignment Keith Busch
2022-05-04 16:32 ` [RFC 3/4] block: add bit bucket support Keith Busch
2022-05-04 16:32 ` [RFC 4/4] nvme: " Keith Busch
2022-05-10 22:41 ` [RFC 0/4] partial sector read support Sagi Grimberg
2022-05-11  0:15   ` Keith Busch

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220504163207.891761-1-kbusch@fb.com \
    --to=kbusch@fb.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=linux-block@kernel.vger.org \
    --cc=linux-nvme@lists.infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox